Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1186 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1903. Min Range: -6.1903
Max Act: 6.1903. Min Act: -0.1700
Data Index: 7955412 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1903. Min Range: -6.1903
Max Act: 6.1591. Min Act: -0.1700
Data Index: 967428 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1903. Min Range: -6.1903
Max Act: 6.1591. Min Act: -0.1700
Data Index: 8346442 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1903. Min Range: -6.1903
Max Act: 6.0341. Min Act: -0.1700
Data Index: 8792059 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1903. Min Range: -6.1903
Max Act: 6.0341. Min Act: -0.1700
Data Index: 993589 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1903. Min Range: -6.1903
Max Act: 6.0028. Min Act: -0.1700
Data Index: 3848471 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.9403. Min Act: -0.1700
Data Index: 566336 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.9403. Min Act: -0.1700
Data Index: 1065839 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.9403. Min Act: -0.1700
Data Index: 8803692 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.9091. Min Act: -0.1700
Data Index: 4928906 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.8778. Min Act: -0.1700
Data Index: 6465696 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.8466. Min Act: -0.1700
Data Index: 2089169 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.8466. Min Act: -0.1700
Data Index: 7885578 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.8466. Min Act: -0.1700
Data Index: 2967863 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.8466. Min Act: -0.1700
Data Index: 4171888 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.8466. Min Act: -0.1700
Data Index: 8607356 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.8778. Min Act: -0.1700
Data Index: 513534 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.8778. Min Act: -0.1700
Data Index: 3779594 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.8153. Min Act: -0.1700
Data Index: 2312505 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1903. Min Range: -6.1903
Max Act: 5.8153. Min Act: -0.1700
Data Index: 7976836 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19